Network representations of digital clock drawings for cognitive impairment detection
- 1Boston University
Abstract
INTRODUCTIONThe digital clock drawing test (dCDT) is a cognitive screening tool capturing high-resolution pen-movement data. Existing approaches for classifying cognitive impairment from dCDTs rely on selected features or image-based methods. We propose representing dCDTs as structural networks to classify cognitive impairment and characterize spatial organization in clock drawings.
METHODSWeighted networks were constructed from 3,362 Framingham Heart Study participants, with and without cognitive impairment. Network representations were generated separately for command and copy conditions, with nodes representing pre-defined clock components (digits, hands, clock face) and edges capturing pairwise spatial relationships between components. Random forest models and graph convolutional networks were trained to predict cognitive impairment from the networks. Models were benchmarked against demographics-only and established summary feature baselines.
RESULTSNetwork-based models achieved AUC values comparable to the established summary feature baseline across command-only and copy-only conditions. Differences in spatial organization between the cognitively intact and impaired groups were greatest in the upper-right clock region, involving digits 1 and 2, the clock hands, and the surrounding clock face. Differences between the command and copy networks were larger among cognitively impaired participants.
DISCUSSIONThe proposed network representations provide an objective, scalable, and flexible framework for representing clock drawings for use in classification models. dCDT networks matched the predictive performance of established summary feature-based approaches and identified clock regions where spatial organization differed by cognitive status. After external validation, this approach has the potential to be incorporated within a clinical workflow to support automated and interpretable cognitive screening.
Related
- Comparative efficacy of exercise modalities for mild cognitive impairment in older adults: A network meta-analysis
- Episodic memory-associated weighted atrophy network mapping in mild cognitive impairment and subjective cognitive decline: a multi-center study
- Comparative efficacy of non-pharmacological interventions for amnestic mild cognitive impairment: a network meta-analysis
- Exploring the Neuroprotective Effects of Walnut (Juglans regia L.) Against Cognitive Impairment in Alzheimer’s Disease Through the MAPK-mTORC1-TFEB-Mediated Endolysosomal Pathway: A Network Pharmacology and Molecular Docking Approach
- Combined metabolomics and network pharmacology explore the protective mechanism of bornyl acetate against cognitive impairment in chronic sleep-deprived mice
BibTeX
@misc{pinheiro2026network,
title = {{Network representations of digital clock drawings for cognitive impairment detection}},
author = {A. Pinheiro and H. Cheng and C. Karjadi and K. Gifford and S. Demissie and K. L. Lunetta and C. Liu and R. Au and S. Mohammed},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.15.26365699},
url = {https://www.medrxiv.org/content/10.64898/2026.10.15.26365699v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Network representations of digital clock drawings for cognitive impairment detection
AU - A. Pinheiro
AU - H. Cheng
AU - C. Karjadi
AU - K. Gifford
AU - S. Demissie
AU - K. L. Lunetta
AU - C. Liu
AU - R. Au
AU - S. Mohammed
PY - 2026
DA - 2026/10/15
PB - medRxiv
DO - 10.64898/2026.10.15.26365699
UR - https://www.medrxiv.org/content/10.64898/2026.10.15.26365699v1
AB - INTRODUCTIONThe digital clock drawing test (dCDT) is a cognitive screening tool capturing high-resolution pen-movement data. Existing approaches for classifying cognitive impairment from dCDTs rely on selected features or image-based methods. We propose representing dCDTs as structural networks to classify cognitive impairment and characterize spatial organization in clock drawings. METHODSWeighted networks were constructed from 3,362 Framingham Heart Study participants, with and without cognitive impairment. Network representations were generated separately for command and copy conditions, with nodes representing pre-defined clock components (digits, hands, clock face) and edges capturing pairwise spatial relationships between components. Random forest models and graph convolutional networks were trained to predict cognitive impairment from the networks. Models were benchmarked against demographics-only and established summary feature baselines. RESULTSNetwork-based models achieved AUC values comparable to the established summary feature baseline across command-only and copy-only conditions. Differences in spatial organization between the cognitively intact and impaired groups were greatest in the upper-right clock region, involving digits 1 and 2, the clock hands, and the surrounding clock face. Differences between the command and copy networks were larger among cognitively impaired participants. DISCUSSIONThe proposed network representations provide an objective, scalable, and flexible framework for representing clock drawings for use in classification models. dCDT networks matched the predictive performance of established summary feature-based approaches and identified clock regions where spatial organization differed by cognitive status. After external validation, this approach has the potential to be incorporated within a clinical workflow to support automated and interpretable cognitive screening.
ER -